© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119606
    Prev
    Next
    INDEX
    Explanations

    recursive behavior

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "recursive" or "Recursive" in programming and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the term “recursive,” i.e. it detects when the text is discussing or labeling something as recursive.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -3.61
     '
    -3.05
     The
    -2.92
    价格
    -2.88
     Your
    -2.66
    可以
    -2.63
     \"
    -2.58
    不錯
    -2.47
    不错
    -2.47
    表现
    -2.41
    POSITIVE LOGITS
    ୌ
    3.08
    辚
    2.98
    下一篇
    2.88
    窠
    2.86
    𓄹
    2.84
    ,,
    2.78
    衪
    2.72
     onItemClick
    2.70
    鋮
    2.67
    犇
    2.66
    Activations Density 0.096%

    No Known Activations